One-click install
npx skills add https://github.com/rjskene/pipeline --skill classify-issue
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: classify-issue
Source: https://github.com/rjskene/pipeline/tree/main/skills/classify-issue
Command: npx skills add https://github.com/rjskene/pipeline --skill classify-issue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the guesswork and delay in triaging GitHub issues by automatically recommending the correct execution path and applying the appropriate pipeline label.

Core Features & Use Cases

  • Trusted triage and guardrails: Refuses to classify when the issue opener lacks write access, then surfaces the issue for human triage.
  • Path recommendation with caching: Uses the latest trusted classification comment to avoid re-classifying unchanged issues and reconciles labels when needed.
  • Deterministic label application: Applies only the docs-only, multi-task, or quick-fix labels with strict allow-list protections.
  • Body marker support: Honors <!-- pipeline:path=[A-D] --> when present to drive classification with high confidence.

Quick Start

Ask for issue triage by running /pipeline:classify-issue <issue_number>.

Frequently Asked Questions about classify-issue

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does trusted author gating work for issue classification?

Yes, body marker support honors the `<!-- pipeline:path=[A-D] -->` HTML comment when present, driving issue classification with high confidence and determining the execution path.

Can I use body markers to control pipeline path routing for issues?

Yes, body marker support honors the `<!-- pipeline:path=[A-D] -->` HTML comment when present, driving issue classification with high confidence and determining the execution path.

What is the best way to avoid re-classifying unchanged GitHub issues?

The skill enforces strict allow-list protections, safely editing only the docs-only, multi-task, and quick-fix labels to prevent unauthorized label modification during issue triage.

What are the limitations of automated issue label application?

The skill enforces strict allow-list protections, safely editing only the docs-only, multi-task, and quick-fix labels to prevent unauthorized label modification during issue triage.